Summary of Onsep: a Novel Online Neural-symbolic Framework For Event Prediction Based on Large Language Model, by Xuanqing Yu et al.
ONSEP: A Novel Online Neural-Symbolic Framework for Event Prediction Based on Large Language Model
by Xuanqing Yu, Wangtao Sun, Jingwei Li, Kang Liu, Chengbao Liu, Jie Tan
First submitted to arxiv on: 14 Aug 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Symbolic Computation (cs.SC)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The Online Neural-Symbolic Event Prediction (ONSEP) framework is a novel technique for temporal knowledge graph forecasting (TKGF). It integrates dynamic causal rule mining (DCRM) and dual history augmented generation (DHAG) to address limitations of previous approaches. ONSEP dynamically constructs causal rules from real-time data, adapting to new relationships, while merging short-term and long-term historical contexts through DHAG. This framework demonstrates notable performance enhancements across diverse datasets, with significant Hit@k improvements, showing its ability to augment large language models (LLMs) for event prediction without extensive retraining. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The ONSEP framework is a new way to predict events based on past experiences and patterns. It’s like trying to figure out what will happen next in a story based on what has happened so far. The old way of doing this relied too heavily on short-term data, which wasn’t very good at adapting to changes or learning from experience. ONSEP is different because it uses two new techniques: dynamic causal rule mining and dual history augmented generation. These tools help the framework learn and adapt faster by combining information from both short-term and long-term historical contexts. |
Keywords
» Artificial intelligence » Knowledge graph
